Random DFAs are Efficiently PAC Learnable
Leonid Aryeh Kontorovich
TL;DR
This paper claims that random deterministic finite automata (DFAs) can be efficiently learned within the Probably Approximately Correct (PAC) framework, suggesting a new approach to automata learning.
Contribution
It introduces a novel theoretical result asserting the PAC learnability of random DFAs, expanding understanding of automata learning complexity.
Findings
Random DFAs are PAC learnable efficiently
Theoretical bounds on learning complexity for random DFAs
Implications for automata learning algorithms
Abstract
This paper has been withdrawn due to an error found by Dana Angluin and Lev Reyzin.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications · Algorithms and Data Compression